{"total":40,"rows":[{"id":"2512.01643","title":"ViT$^3$: Unlocking Test-Time Training in Vision","created":"2025-12-01","cited_by_count":18,"area":null},{"id":"2507.00698","title":"Rectifying Magnitude Neglect in Linear Attention","created":"2025-07-01","cited_by_count":16,"area":null},{"id":"2510.22049","title":"Massive Memorization with Hundreds of Trillions of Parameters for Sequential Transducer Generative Recommenders","created":"2025-10-24","cited_by_count":10,"area":null},{"id":"2601.07832","title":"MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head","created":"2026-01-12","cited_by_count":7,"area":null},{"id":"2507.23632","title":"On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective","created":"2025-07-31","cited_by_count":6,"area":null},{"id":"2602.05230","title":"ZeroS: Zero-Sum Linear Attention for Efficient Transformers","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2510.05364","title":"The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures","created":"2025-10-06","cited_by_count":4,"area":null},{"id":"2511.00833","title":"Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials","created":"2025-11-02","cited_by_count":4,"area":null},{"id":"2602.02180","title":"STILL: Selecting Tokens for Intra-Layer Hybrid Attention to Linearize LLMs","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2602.18283","title":"HyTRec: A Hybrid Temporal-Aware Attention Architecture for Long Behavior Sequential Recommendation","created":"2026-02-20","cited_by_count":4,"area":null},{"id":"2603.16063","title":"ViT-AdaLA: Adapting Vision Transformers with Linear Attention","created":"2026-03-17","cited_by_count":4,"area":null},{"id":"2502.07553","title":"Transformers Provably Learn Sparse XOR with Polylogarithmic Parameters","created":"2025-02-11","cited_by_count":3,"area":null},{"id":"2502.18277","title":"Self-Adjust Softmax","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2509.12817","title":"SAGA: Selective Adaptive Gating for Efficient and Expressive Linear Attention","created":"2025-09-16","cited_by_count":3,"area":null},{"id":"2509.18467","title":"LAWCAT: Efficient Distillation from Quadratic to Linear Attention with Convolution across Tokens for Long Context Modeling","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2602.23057","title":"Affine-Scaled Attention: Towards Flexible and Stable Transformer Attention","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2604.20368","title":"LaplacianFormer:Rethinking Linear Attention with Laplacian Kernel","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2605.02772","title":"Linearizing Vision Transformer with Test-Time Training","created":"2026-05-04","cited_by_count":3,"area":null},{"id":"2503.10632","title":"Kolmogorov-Arnold Attention: Is Learnable Attention Better For Vision Transformers?","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2506.21137","title":"Norm$\\times$Direction: Restoring the Missing Query Norm in Vision Linear Attention","created":"2025-06-26","cited_by_count":2,"area":null},{"id":"2503.01873","title":"Online Pseudo-average Shifting Attention(PASA) for Robust Low-precision LLM Inference: Algorithms and Numerical Analysis","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2510.25753","title":"How Data Mixing Shapes In-Context Learning: Asymptotic Equivalence for Transformers with MLPs","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2511.01292","title":"Optimal Attention Temperature Improves the Robustness of In-Context Learning under Distribution Shift in High Dimensions","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2602.01744","title":"Softmax Linear Attention: Reclaiming Global Competition","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2608.22368","title":"DiD It in 87 Minutes: A Label-Free Softmax-to-Linear Adaptation of Vision Transformers for Object Detection","created":"2026-08-23","cited_by_count":1,"area":null},{"id":"2505.19472","title":"Balancing Computation Load and Representation Expressivity in Parallel Hybrid Neural Networks","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2506.08226","title":"Mondrian: Transformer Operators via Domain Decomposition","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2506.12453","title":"Topology-Assisted Spatio-Temporal Pattern Disentangling for Scalable MARL in Large-scale Autonomous Traffic Control","created":"2025-06-14","cited_by_count":0,"area":null},{"id":"2510.11789","title":"Minimax Rates for Learning Pairwise Interactions in Attention-Style Models","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2510.20092","title":"Attentive Convolution: Unifying the Expressivity of Self-Attention with Convolutional Efficiency","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2601.22630","title":"LINA: Linear Autoregressive Image Generative Models with Continuous Tokens","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.04346","title":"MirrorLA: Reflecting Feature Map for Vision Linear Attention","created":"2026-02-04","cited_by_count":0,"area":null},{"id":"2603.00611","title":"Exploring Spatiotemporal Feature Propagation for Video-Level Compressive Spectral Reconstruction: Dataset, Model and Benchmark","created":"2026-02-28","cited_by_count":0,"area":null},{"id":"2604.03850","title":"Collapse-Free Prototype Readout Layer for Transformer Encoders","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2605.17294","title":"HierEdit: Region-Aware Hierarchical Diffusion for Efficient High-Resolution Editing","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2606.27372","title":"DnA: Denoising Attention for Visual Tasks","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2608.29609","title":"nnMNet: Baseline for Martian Terrain Semantic Segmentation","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.35745","title":"Copy the Same, Distill the Difference: Initializing Linear Vision Transformers","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.39034","title":"Switching Linear Attention","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39914","title":"Cluster Attention Neural Operators for Solving Parametric Partial Differential Equations","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}